cognitive-load-theory
Warn
Audited by Snyk on Aug 22, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). SKILL.md defines the cognitive-load-theory skill’s runtime “Coach mode” as eliciting and diagnosing the user’s own free-form learner/design failure signals via interactive [WAIT] prompts, so the agent ingests outsider-authored text from the conversation without selecting a specific trusted item.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata